2-Steps Approach for Both Rotor and Bearing Faults Identification in Rotating Machines Using Measured Vibration Responses

An earlier study has proposed the 2-Steps approach for the rotor-related faults only using the measured vibration responses on the bearing housings on a rotating rig. The method has used the vibration parameters in both time and frequency domains calculated from the measured vibration responses at each bearing and the artificial neural network (ANN) based machine learning (ML) models to identify the machine health condition. Step-1 determines whether the machine is healthy or faulty. Then, in Step-2, only faulty conditions data are used to identify the exact nature of the faults. In the current study, this 2-Steps Approach is further extended and examined to both rotor and anti-friction bearing faults. The vibration parameters are revised to include bearing-related faults. This exercise has been done on the measured vibration data from a laboratory-scaled rotating rig. The extended study presents new insights and findings built on the previous work. This study can be a valuable contribution to predictive maintenance. It demonstrates its effectiveness in diagnosing faults in rotating machines, reducing the risk of failure, and enhancing reliability in industrial operations.